© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7951
    Prev
    Next
    INDEX
    Explanations

    visible perception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मॉडलिंग
    1.08
    狠
    1.06
    噱
    0.95
     relentlessly
    0.93
     momentum
    0.92
     ritmo
    0.90
     adiabatic
    0.89
    番
    0.88
    ով
    0.87
     automating
    0.86
    POSITIVE LOGITS
     clearly
    1.32
    clearly
    1.31
     plainly
    1.23
     claramente
    1.13
     jelas
    1.11
     Clearly
    1.07
     clearest
    1.05
     स्पष्ट
    1.02
     através
    1.01
     través
    1.00
    Activations Density 0.183%

    No Known Activations